Welcome to Jetson AGX Thor repository
2.Install large model dialogue platform
Open WebUI
Open WebUI1. Environment Requirements2. Docker Setup2.1 Official Docker Installation2.2 Installing Docker on Alibaba Cloud2.3. Granting Access Permissions3. Open WebUI Installation4. Running Open WebUI4.1. Administrator Account4.2. Registration and Login4.3. User Interface5. Model Conversation5.1. Switching Models5.2. Demo: LLaVA6. Frequently Asked Questions6.1. Shutting Down Open WebUI6.2. Common ErrorsUnable to Start Open WebUIService Connection Timeout
Open WebUI is an open-source project designed to provide a simple and easy-to-use user interface (UI) for managing and monitoring open-source software and services.
xxxxxxxxxxWhen using Open WebUI, there's a high probability of encountering unresponsive or timeout issues. Try restarting Open WebUI or using the Ollam tool to run the model!
1. Environment Requirements
Installing Open WebUI on the host machine and Conda: Requires Node.js >= 20.10, Python = 3.11:
| Environment Setup Method | Difficulty (relatively speaking) |
|---|---|
| Host | High |
| Conda | Medium |
| Docker | Low |
This tutorial demonstrates installing Open WebUI using Docker.
2. Docker Setup
2.1 Official Docker Installation
If Docker is not installed, you can use a script to install it with one click.
Domestic users may not be able to install Docker through official methods. We recommend using Alibaba Cloud to install Docker or directly using our image.
- Update local package list
xxxxxxxxxxsudo apt update
- Download and run script
Download the get-docker.sh file and save it in the current directory.
xxxxxxxxxxsudo apt install curl
xxxxxxxxxxcurl -fsSL https://get.docker.com -o get-docker.sh
Run the get-docker.sh script file with sudo privileges.
xxxxxxxxxxsudo sh get-docker.sh
2.2 Installing Docker on Alibaba Cloud
If you cannot install it yourself, please use the image we provide.
- Update the local package list
xxxxxxxxxxsudo apt update
- Install prerequisites
xxxxxxxxxxsudo apt install apt-transport-https ca-certificates curl gnupg2 lsb-release software-properties-common
- Add the GPG key for the software repository
xxxxxxxxxxcurl -fsSL https://mirrors.aliyun.com/docker-ce/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
- Add the Alibaba Cloud mirror repository
xxxxxxxxxxecho "deb [arch=arm64 signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://mirrors.aliyun.com/docker-ce/linux/ubuntu bionic stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
- Install Docker
xxxxxxxxxxsudo apt updatesudo apt install docker-ce docker-ce-cli containerd.io docker-compose-plugin
2.3. Granting Access Permissions
Grant the current system user access to the Docker daemon: this allows you to execute Docker commands without needing to use the sudo command.
xxxxxxxxxxsudo usermod -aG docker $USERnewgrp docker
3. Open WebUI Installation
For systems that already have Docker installed, you can simply enter the following command in the terminal. (The image below shows the result after the Docker image has been successfully pulled.)
xxxxxxxxxxdocker pull ghcr.io/open-webui/open-webui:main

4. Running Open WebUI
Enter the following command in the terminal to launch the specified Docker container:
xxxxxxxxxxdocker run --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main

Once successfully launched, access the interface via your browser using the following URL:
xxxxxxxxxxhttp://localhost:8080/
Within the same local area network (LAN), you can access the service using the mainboard's IP address followed by :8080:
xxxxxxxxxxAssuming the mainboard's IP address is 192.168.2.105, you can access it via 192.168.2.105:8080.
4.1. Administrator Account
For first-time use, you are required to register an account. This account will serve as the administrator account; please fill in the required information as prompted.
xxxxxxxxxxSince all content within our provided Docker image has been pre-configured and tested, users can simply log in directly using the following pre-registered account:Username: yahboomEmail: yahboom@163.comPassword: yahboom
4.2. Registration and Login



4.3. User Interface

5. Model Conversation
Engaging in conversations via Open WebUI is slower than running directly through the Ollama tool; you may even encounter connection timeouts or service failures. This is directly related to the memory limitations of the Jetson board and is unavoidable.
xxxxxxxxxxUsers who wish to avoid this issue may consider switching to a different Linux environment to set up Ollama and Open WebUI for their conversations.
5.1. Switching Models
Click Select a model to choose a specific model for your conversation.
xxxxxxxxxxModels pulled using Ollama are automatically added to the Open WebUI model selection list; simply refresh the webpage to see the newly added models!

5.2. Demo: LLaVA
The LLaVA demonstration case requires at least 8GB of memory (or more) to run; users may use other cases to test the conversational features of Open WebUI!
xxxxxxxxxxWhat's in this image?

6. Frequently Asked Questions
6.1. Shutting Down Open WebUI
Disabling the auto-starting Open WebUI service. - View running Docker containers
xxxxxxxxxxdocker ps
- Stop a running Docker container
xxxxxxxxxxdocker stop [CONTAINER ID] # Example: docker stop 5f42ee9cf784
- View stopped containers
xxxxxxxxxxdocker ps -a
- Clean up stopped containers
xxxxxxxxxxdocker rm [CONTAINER ID] # Example: docker rm 5f42ee9cf784
Clean up all stopped containers:
xxxxxxxxxxdocker container prune
6.2. Common Errors
Unable to Start Open WebUI
- docker: Error response from daemon: Conflict. The container name "/open-webui" is already in use by container "cfc05c84f8e38b290337e7178c76fd1c49076f94b11ed3d49d9448be72b7f20f". You have to remove (or rename) that container to be able to reuse that name.
Solution: Stop Open WebUI once and then restart it!
Service Connection Timeout
- Open WebUI: Server Connection Error
Stop Open WebUI once and then restart it; then, try submitting your query again, or switch to using the Ollama tool directly to run the model and submit your query there!